© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 68647
    Prev
    Next
    INDEX
    Explanations

    .NET code initialization (`ISupportInitialize` `BeginInit`)

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ↵
    -2.20
     who
    -2.09
     them
    -1.77
     tecnologías
    -1.64
    というのも
    -1.62
     "
    -1.62
     to
    -1.54
     cív
    -1.51
    :
    -1.50
    -1.49
    POSITIVE LOGITS
     ''}
    1.63
    گوشی
    1.58
    ING
    1.57
    schirm
    1.52
     denna
    1.47
     行っ
    1.46
    ğlık
    1.46
    tamaan
    1.45
     tämän
    1.45
    uelles
    1.45
    Activations Density 0.000%
    No Known Activations